You can deploy this model and start earning money today!

RichardErkhov/
yys_-_gemma-7B-it-firefly-gguf

Name: yys_-_gemma-7B-it-firefly-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-7B-it-firefly - GGUF

Model creator: https://huggingface.co/yys/
Original model: https://huggingface.co/yys/gemma-7B-it-firefly/

Name	Quant method	Size
gemma-7B-it-firefly.Q2_K.gguf	Q2_K	3.24GB
gemma-7B-it-firefly.IQ3_XS.gguf	IQ3_XS	3.54GB
gemma-7B-it-firefly.IQ3_S.gguf	IQ3_S	3.71GB
gemma-7B-it-firefly.Q3_K_S.gguf	Q3_K_S	3.71GB
gemma-7B-it-firefly.IQ3_M.gguf	IQ3_M	3.82GB
gemma-7B-it-firefly.Q3_K.gguf	Q3_K	4.07GB
gemma-7B-it-firefly.Q3_K_M.gguf	Q3_K_M	4.07GB
gemma-7B-it-firefly.Q3_K_L.gguf	Q3_K_L	4.39GB
gemma-7B-it-firefly.IQ4_XS.gguf	IQ4_XS	4.48GB
gemma-7B-it-firefly.Q4_0.gguf	Q4_0	4.67GB
gemma-7B-it-firefly.IQ4_NL.gguf	IQ4_NL	4.69GB
gemma-7B-it-firefly.Q4_K_S.gguf	Q4_K_S	4.7GB
gemma-7B-it-firefly.Q4_K.gguf	Q4_K	4.96GB
gemma-7B-it-firefly.Q4_K_M.gguf	Q4_K_M	4.96GB
gemma-7B-it-firefly.Q4_1.gguf	Q4_1	5.12GB
gemma-7B-it-firefly.Q5_0.gguf	Q5_0	5.57GB
gemma-7B-it-firefly.Q5_K_S.gguf	Q5_K_S	5.57GB
gemma-7B-it-firefly.Q5_K.gguf	Q5_K	5.72GB
gemma-7B-it-firefly.Q5_K_M.gguf	Q5_K_M	5.72GB
gemma-7B-it-firefly.Q5_1.gguf	Q5_1	6.02GB
gemma-7B-it-firefly.Q6_K.gguf	Q6_K	6.53GB
gemma-7B-it-firefly.Q8_0.gguf	Q8_0	8.45GB

Original model description:

library_name: transformers license: apache-2.0 basemodel: google/gemma-7b-it

Model Card for Firefly-Gemma

gemma-7B-it-firefly is trained based on gemma-7b-it to act as a helpful and harmless AI assistant. we trained the model on firefly-train-1.1M dataset using LoRA.

Performance

we evaluate the model on Open LLM Leaderboard

Usage

The chat template of our chat models is same as Official gemma-7b-it:

text

<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model

You can also use the following code:

python

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name_or_path = "yys/gemma-7B-it-firefly"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path)

input_text = "给我写一首关于机器学习的诗歌。"
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

RichardErkhov/yys_-_gemma-7B-it-firefly-gguf